Robot cafes on every street corner might still be a way off but the idea is less far fetched thanks to a major Australian advance in the field of mechatronics.
The University of Adelaide’s Dr Habib Habibullah and his colleagues have devised an improved algorithm to help mobile robots avoid crashing into humans and other moving obstacles in their path.
No longer will future diners need to worry if their lattes and macarons will arrive in one piece.
As well as making sure robots can recognise and avoid obstructions, the computer model also allows them to efficiently navigate the quickest and easiest path to their destination.
Dr Habibullah says combining the best of existing algorithms to create a collision-free TurtleBot able to adjust its speed and steering angles proved somewhat exacting.
“There are two types of path planning strategies for mobile robots, depending on whether they are being used in fixed environments or where they are encountering moving obstacles, such as humans or machines,” he said.
“The first is fairly easily to program but the second is more challenging.”
While there are several algorithms on the market designed to minimise collision avoidance, none have have been declared foolproof.
The UniSA team tested its model against two common collision avoidance algorithms and found theirs came up trumps.
In a series of simulations in nine different scenarios they compared collision rates, average time to destination and average speed of the robot.
In every scenario, the UniSA-designed algorithm helped robots successfully navigate a path without mishap.
One of the two comparison models was 66 per cent effective, colliding with objects in three of the nine simulations.
The other was also collision-free but took more time to reach its destination.
“Our proposed method sometimes took a longer path but it was faster and safer, avoiding all collisions,” Dr Habibullah said.
Mobile robots are an increasingly important element of logistics but generally operate alongside humans. The exception is in warehouse scenarios like those utilised by e-commerce behemoth Amazon.
The company uses an army of robot-wheeled shelf units to select purchases, read barcodes and deliver goods to counters for packaging, presumably without collecting human workers along the way.
Dr Habibullah says his algorithm could be applied not only in industrial warehouses but for fruit picking, packing and pelletising, and also for restaurant robots that deliver food from the kitchen to the table.
In terms of mechanics, his team was able to direct their TurtleBot to stop, turn and even reverse direction if it encountered anything in its path.
“This could also be a potential solution for agricultural robots, for example autonomous lawn mowers, ground robots for crop surveillance and autonomous weeding robots, where children, pets and other animals are often present,” he said.